Model: GELU Model: 1 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1659 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gelu-1l')

Click the toggle to see the full text!

Text #0

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.6106. Min Act: -0.1700

Data Index: 1088930 (C4 (Web Text))

Max Activating Token Index: 82

Text #1

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.5906. Min Act: -0.1700

Data Index: 335664 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.5048. Min Act: -0.1700

Data Index: 1473351 (Python Code)

Max Activating Token Index: 916

Text #3

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.5171. Min Act: -0.1700

Data Index: 1036219 (C4 (Web Text))

Max Activating Token Index: 713

Text #4

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.4665. Min Act: -0.1699

Data Index: 438260 (C4 (Web Text))

Max Activating Token Index: 846

Text #5

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.4640. Min Act: -0.1700

Data Index: 584773 (C4 (Web Text))

Max Activating Token Index: 887

Text #6

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.4707. Min Act: -0.1700

Data Index: 936062 (C4 (Web Text))

Max Activating Token Index: 786

Text #7

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.3938. Min Act: -0.1700

Data Index: 1393345 (Python Code)

Max Activating Token Index: 485

Text #8

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.4520. Min Act: -0.1700

Data Index: 182860 (C4 (Web Text))

Max Activating Token Index: 605

Text #9

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.3502. Min Act: -0.1700

Data Index: 1533971 (Python Code)

Max Activating Token Index: 443

Text #10

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.3916. Min Act: -0.1699

Data Index: 939527 (C4 (Web Text))

Max Activating Token Index: 682

Text #11

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.3639. Min Act: -0.1700

Data Index: 1072425 (C4 (Web Text))

Max Activating Token Index: 785

Text #12

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.3466. Min Act: -0.1700

Data Index: 57283 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.3258. Min Act: -0.1700

Data Index: 567249 (C4 (Web Text))

Max Activating Token Index: 539

Text #14

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.3384. Min Act: -0.1700

Data Index: 13907 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.3380. Min Act: -0.1700

Data Index: 1110868 (C4 (Web Text))

Max Activating Token Index: 784

Text #16

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.2446. Min Act: -0.1700

Data Index: 473780 (C4 (Web Text))

Max Activating Token Index: 897

Text #17

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.2185. Min Act: -0.1700

Data Index: 590821 (C4 (Web Text))

Max Activating Token Index: 682

Text #18

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.1968. Min Act: -0.1700

Data Index: 411266 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 4.6106. Min Range: -4.6106

Max Act: 4.2415. Min Act: -0.1700

Data Index: 1074990 (C4 (Web Text))

Max Activating Token Index: 456